SShogo Bench

GPT-6 Sol vs Qwen3.8 Max Preview

GPT-6 Sol leads Qwen3.8 Max Preview by 10.0 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-6 Sol wins 12 and Qwen3.8 Max Preview wins 2 of 14 shared benchmarks. Qwen3.8 Max Preview is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-6 SolQwen3.8 Max Preview
Agentic coding7258
Long-horizon autonomy7663
Knowledge-work agents4846
Computer use5441
Security & context learning5952

Shared benchmarks

BenchmarkGPT-6 SolQwen3.8 Max Preview
APEX-Agentsindex54.3%63.3%
Chess Puzzles56.0%46.0%
CritPt30.9%20.0%
DTBench97.3%92.0%
FrontierMath Tier 490.0%46.3%
FrontierMath Tiers 1-389.8%74.7%
GPQA Diamond94.3%92.7%
LMCA59.1%46.2%
MirrorCode48.9%52.2%
OTIS Mock AIME100.0%99.4%
ProofBench83.0%58.0%
SciCode57.6%53.2%
SimpleQA Verified60.7%45.8%
WebDev Arena16891671

Specs and price

GPT-6 SolQwen3.8 Max Preview
Agent Index63.6 (#13)53.6 (#30)
Agent $/M$0.92Free
Input / output $/M$2.00 / $10.00Free / Free
Context1.1M1M
ReleasedSep 22, 2026Jul 19, 2026
WeightsClosedClosed
API hosts51

Don’t pick one. Route.

Shogo can run GPT-6 Sol and Qwen3.8 Max Preview side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo